© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65912
    Prev
    Next
    INDEX
    Explanations

    online information and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -2.11
     even
    -1.81
     my
    -1.70
     I
    -1.66
    :
    -1.52
     some
    -1.43
     cuando
    -1.38
     nuestra
    -1.38
     when
    -1.34
     two
    -1.34
    POSITIVE LOGITS
    ּוֹ
    1.89
     бампер
    1.62
    ̴
    1.49
    ͚
    1.42
     artificiales
    1.37
     Ministère
    1.37
    çamento
    1.30
    ῖ
    1.28
    腟
    1.24
     notizie
    1.23
    Activations Density 0.018%

    No Known Activations